Fast committee learning can, to some extent, achieve the generalisation advantages of a committee of neural networks, without the need for independent learning of the committee members. This is achieved by selecting committee members from time-slices of the learning trajectory of one neural network.
References
-
-
1)
-
Breiman, L.: `Stacked regression', 367, Technical Report, 1992.
-
2)
-
A. Sharkey
.
On combining artificial neural networks.
Connect. Sci.
,
299 -
314
-
3)
-
Partridge, D., Griffith, N.: `Strategies for improving neural net generalization', 301, Research Report, 1994.
-
4)
-
D. Wolpert
.
Stacked generalization.
Neural Netw.
,
241 -
259
-
5)
-
Prechelt, L.: `Proben1 - A set of neural network benchmark problems and benchmarkingrules', 21/94, Technical Report, 1994.
-
6)
-
B. Fritzke
.
(1995)
A growing neural gas network learns topologies, Advances in Neural Information Processing Systems 7.
-
7)
-
T. Kohonen
.
Self-organized formation of topologically correct feature maps.
Biol. Cybern.
,
59 -
69
-
8)
-
J. Moody ,
C.J. Darken
.
Fast learning in networks of locally-tuned processing units.
Neural Comput.
,
281 -
294
-
9)
-
Fritzke, B.: `Growing cell structures - A self-organizing network for unsupervisedand supervised learning', Technical Report, 93-026, 1993.
-
10)
-
B. Fritzke
.
Fast learning with incremental RBF networks.
Neural Process. Lett.
,
1 ,
2 -
5
-
11)
-
Hamker, F., Heinke, D.: `Implementation and comparison of growing neural gas, growing cell structuresand fuzzy artmap', 1/97, Technical Report, 1997.
-
12)
-
T. Martinetz ,
K. Schulten ,
T. Kohonen ,
K. Makisara ,
O. Simula ,
J. Kangas
.
(1991)
A ‘neural-gas’ network learns topologies, Artificial neural networks.
http://iet.metastore.ingenta.com/content/journals/10.1049/el_19981000
Related content
content/journals/10.1049/el_19981000
pub_keyword,iet_inspecKeyword,pub_concept
6
6